© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31680
    Prev
    Next
    INDEX
    Explanations

    flying, fly, or flew

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ຟ
    0.48
    DECL
    0.47
    孅
    0.47
    )<<
    0.43
    IGENCE
    0.43
    .‏
    0.43
     aden
    0.43
    smanship
    0.43
    л
    0.43
    ಫ
    0.43
    POSITIVE LOGITS
     flying
    0.79
    Flying
    0.79
    flying
    0.78
     Flying
    0.75
    飞
    0.65
     saucer
    0.63
     flew
    0.61
    飛
    0.55
    Fly
    0.54
    fly
    0.52
    Activations Density 0.002%

    No Known Activations